Reinforcement Learning (RL) faces challenges in transferring knowledge across tasks efficiently. In this work we focus on transferring policies between different temporally extended tasks expressed in Linear Temporal Logic. Existing methodologies either rely on task-specific representations or...
04b Atto di convegno in volume
-
Transfer Learning between non-Markovian RL Tasks through Semantic Representations of Temporal States
-
In process mining, declarative process discovery aims to extract declarative process models from event logs. Declare is a declarative process modeling language that provides an extensible set of standard templates for modeling declarative processes imposing temporal constraints on the sequence of...
-
Self-protecting systems heavily depend on the quality of information in input in the adaptation loop. Among the others, device and vulnerability inventories play a fundamental role in such systems, and improving their quality is paramount. This paper proposes a new version-based algorithm to filter...
-
As cyber threats continue to evolve, the need for highly skilled cyber defence operators becomes increasingly critical. In this work, we aim to provide a multidisciplinary exploration into the current educational landscape, focusing on the following pivotal areas: cyber defence educational...
-
Self-protection is a desired property of many modern ICT systems as it enriches them in detecting and reacting to security threats at run-time. Several solutions leveraging vulnerability scanners and attack graphs have recently been proposed to monitor and analyze cyber risks and trigger security...
-
Inventories are precious sources of information for security-related processes. As a consequence, the quality of the data in the inventories plays a crucial role in the overall quality of the fed processes. This paper takes this challenge and provides heuristics to improve the accuracy of...
-
The increasing number of cyberattacks against critical infrastructures has pushed researchers to develop many Visual Analytics solutions to provide valid defensive approaches and improve the situational awareness of the security operators. Applying such solutions to complex infrastructures is often...
-
We present Lemming – a visualization tool for the interactive selection of plans for a given problem, allowing the user to efficiently whittle down the set of plans and select their plan(s) of choice. We demonstrate four different user experiences for this process, three of them based on the...
-
In this paper, we propose the use of epistemic dependencies to express data protection policies in Controlled Query Evaluation (CQE), which is a form of confidentiality-preserving query answering over ontologies and databases. The resulting policy language goes significantly beyond those proposed...
-
Motivated by recent work in computational social choice, we extend the metric distortion framework to clustering problems. Given a set of n agents located in an underlying metric space, our goal is to partition them into k clusters, optimizing some social cost objective. The metric space is defined...